A Model to Predict Upstaging to Invasive Carcinoma in Patients Preoperatively Diagnosed with Low-Grade Ductal Carcinoma In Situ of the Breast

Nicosia, Luca; Bozzini, Anna Carla; Penco, Silvia; Trentin, Chiara; Pizzamiglio, Maria; Lazzeroni, Matteo; Lissidini, Germana; Veronesi, Giulia; Farante, G.; Frassoni, Samuele; Bagnardi, Vincenzo; Fodor, C.; Fusco, Nicola; Sajjadi, Elham; Cassano, Enrico; Pesapane, Filippo

doi:10.3390/cancers14020370

Cited by 6 publications

(7 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…12 Past models utilizing radiological and/or pathological features to predict upstaging have achieved AUCs ranging from 0.62 to 0.85. 7,8,[30][31][32][33][34][35][36][37][38] However, only very few of these models were independently validated. Our study was the first to integrate artificial intelligence-based digital pathology into a prediction model, and the model was validated in an independent dataset.…”

Section: Discussionmentioning

confidence: 99%

“…5 Thus, a correct risk stratification of these precursor lesions is fundamental when planning treatment strategies, and possible predictors for upstaging ductal DCIS to invasive carcinoma have been identified, such as palpability, tumour size, radiological features, biopsy methods, and histological grading. [6][7][8][9] Nevertheless, this process is limited by the significant interobserver variability in the grading of DCIS by human pathologists, as demonstrated in previous studies. 10,11 Deep-learning-based computational pathology has become a powerful tool for histological diagnosis, grading, and survival prediction.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deep‐learning model to improve histological grading and predict upstaging of atypical ductal hyperplasia / ductal carcinoma in situ on breast biopsy

Huang,

Chang,

Lin

et al. 2024

Histopathology

View full text Add to dashboard Cite

AimsRisk stratification of atypical ductal hyperplasia (ADH) and ductal carcinoma in situ (DCIS), diagnosed using breast biopsy, has great clinical significance. Clinical trials are currently exploring the possibility of active surveillance for low‐risk lesions, whereas axillary lymph node staging may be considered during surgical planning for high‐risk lesions. We aimed to develop a machine‐learning algorithm based on whole‐slide images of breast biopsy specimens and clinical information to predict the risk of upstaging to invasive breast cancer after wide excision.Methods and ResultsPatients diagnosed with ADH/DCIS on breast biopsy were included in this study, comprising 592 (740 slides) and 141 (198 slides) patients in the development and independent testing cohorts, respectively. Histological grading of the lesions was independently evaluated by two pathologists. Clinical information, including biopsy method, lesion size, and Breast Imaging Reporting and Data System (BI‐RADS) classification of ultrasound and mammograms, were collected. Deep DCIS consisted of three deep neural networks to evaluate nuclear grade, necrosis, and stromal reactivity. Deep DCIS output comprised five parameters: total patches, lesion extent, Deep Grade, Deep Necrosis, and Deep Stroma. Deep DCIS highly correlated with the pathologists' evaluations of both slide‐ and patient‐level labels. All five parameters of Deep DCIS were significantly associated with upstaging to invasive carcinoma in subsequent wide excisional specimens. Using multivariate logistic regression, Deep DCIS predicted upstaging to invasive carcinoma with an area under the curve (AUC) of 0.81, outperforming pathologists' evaluation (AUC, 0.71 and 0.69). After including clinical and hormone receptor status information, performance further improved (AUC, 0.87). This combined model retained its predictive power in two subgroup analyses: the first subgroup included unequivocal DCIS (excluding cases of ADH and DCIS suspicious for microinvasion) (AUC, 0.83), while the second excluded cases of high‐grade DCIS (AUC, 0.81). The model was validated in an independent testing cohort (AUC, 0.81).ConclusionThis study demonstrated that deep‐learning models can refine histological evaluation of ADH and DCIS on breast biopsies, which may help guide future treatment planning.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Deep‐learning model to improve histological grading and predict upstaging of atypical ductal hyperplasia / ductal carcinoma in situ on breast biopsy

Huang,

Chang,

Lin

et al. 2024

Histopathology

View full text Add to dashboard Cite

show abstract

“…This may be important when evaluating those patients in whom a diagnostic underestimation (those patients who have an in-situ neoplasm as a result of biopsy and are found to have an infiltrating neoplasm at surgery) of the biopsy with results of DCIS is suspected: a particular type of enhancement may lead to suspect an invasive lesion rather than an in situ one [ 46 , 47 , 48 ].…”

Section: Discussionmentioning

confidence: 99%

A Score to Predict the Malignancy of a Breast Lesion Based on Different Contrast Enhancement Patterns in Contrast-Enhanced Spectral Mammography

Nicosia

Bozzini

Palma

et al. 2022

Cancers

Self Cite

View full text Add to dashboard Cite

Background: To create a predictive score of malignancy of a breast lesion based on the main contrast enhancement features ascertained by contrast-enhanced spectral mammography (CESM). Methods: In this single-centre prospective study, patients with suspicious breast lesions (BIRADS > 3) were enrolled between January 2013 and February 2022. All participants underwent CESM prior to breast biopsy, and eventually surgery. A radiologist with 20 years’ experience in breast imaging evaluated the presence or absence of enhancement and the following enhancement descriptors: intensity, pattern, margin, and ground glass. A score of 0 or 1 was given for each descriptor, depending on whether the enhancement characteristic was predictive of benignity or malignancy (both in situ and invasive). Then, an overall enhancement score ranging from 0 to 4 was obtained. The histological results were considered the gold standard in the evaluation of the relationship between enhancement patterns and malignancy. Results: A total of 321 women (median age: 51 years; range: 22–83) with 377 suspicious breast lesions were evaluated. Two hundred forty-nine lesions (66%) have malignant histological results (217 invasive and 32 in situ). Considering an overall enhancement score ≥ 2 as predictive of malignancy, we obtain an overall sensitivity of 92.4%; specificity of 89.8%; positive predictive value of 94.7%; and negative predictive value of 85.8%. Conclusions: Our proposed predictive score on the enhancement descriptors of CESM to predict the malignancy of a breast lesion shows excellent results and can help in early breast cancer diagnosis and in avoiding unnecessary biopsies.

show abstract

“…In this article, based on our experience, we aim to provide an appropriate diagnostic and therapeutic approach for this rare condition. Radiological, histological, and clinical features in male DCIS differ from DCIS in women, and for adequate management, the knowledge of two different forms of the same pathology appears extremely important [ 17 , 18 , 19 , 20 , 21 ]. In our series, pure DCIS was observed in 21/233 cases (9.0%).…”

Section: Discussionmentioning

confidence: 99%

“… The therapeutic treatment of choice (also to reduce the rate of recurrence) should be mastectomy with associated sentinel lymph node biopsy: it is estimated that up to 26% of patients with a preoperative diagnosis of DCIS are upgraded to invasive carcinoma on final postoperative histological examination [ 27 ]. In view of this axillary evaluation, including SLNB, could be justified in male DCIS patients undergoing mastectomy because of the possibility of upstaging to invasive cancer at surgery: vacuum-assisted biopsy (especially with macroscopic removal of the lesion) is the best way to decrease biopsy underestimation in breast DCIS [ 17 ], anyway the poor of the breast thickness makes the vacuum-assisted breast biopsy scarcely used in males. If the decision is made not to use sentinel lymph node biopsy in the male with DCIS, an extemporaneous intraoperative diagnostic examination of the surgical piece is suggested to confirm the in situ nature of the neoplasm.…”

Section: Discussionmentioning

confidence: 99%

Ductal carcinoma in situ of the male breast: clinical radiological features and management in a cancer referral center

Nicosia

Lissidini

Sargenti

et al. 2022

Breast Cancer Res Treat

View full text Add to dashboard Cite

Purpose To present an overview of the management of male patients with Ductal Carcinoma In Situ of the breast (male DCIS). Methods We retrospectively studied all male patients with a diagnosis of pure DCIS from January 1999 to December 2018: 20 patients were identified in our cancer referral center. We collected data regarding clinical presentation, age of onset, radiological features, receptor status of the neoplasm, histological type, and the follow-up of those patients. Results The median age was 62 years (range 21–80). All patients underwent surgery, in 15/20 (75%) cases a mastectomy was carried out. Two patients (10%) underwent endocrine treatment and 1/20 (5%) underwent radiotherapy. The receptor status for 15/20 patients was documented: 13/15 patients were ER+/Pr+. In 3 cases the Ki 67% was positive (i.e., > 20%). All cases were negative for Her2. The median follow-up time was 9.0 years (IQR 4.0–13.7). Only one patient had an ipsilateral recurrence with the finding of an infiltrating carcinoma in the same breast after 14 years. The 5-year disease-free survival was 92.9%. Conclusion Pure DCIS in men is an extremely rare disease: proper diagnosis and management allow an excellent prognosis.

show abstract

A Model to Predict Upstaging to Invasive Carcinoma in Patients Preoperatively Diagnosed with Low-Grade Ductal Carcinoma In Situ of the Breast

Cited by 6 publications

References 29 publications

Deep‐learning model to improve histological grading and predict upstaging of atypical ductal hyperplasia / ductal carcinoma in situ on breast biopsy

Deep‐learning model to improve histological grading and predict upstaging of atypical ductal hyperplasia / ductal carcinoma in situ on breast biopsy

A Score to Predict the Malignancy of a Breast Lesion Based on Different Contrast Enhancement Patterns in Contrast-Enhanced Spectral Mammography

Ductal carcinoma in situ of the male breast: clinical radiological features and management in a cancer referral center

Contact Info

Product

Resources

About