Tumor burden of lung metastases at initial staging in breast cancer patients detected by artificial intelligence as a prognostic tool for precision medicine

Kocher, Madison; Chamberlin, Jordan; Waltz, Jeffrey; Snoddy, Madalyn; Stringer, Natalie; Stephenson, Joseph; Kahn, Jacob; Mercer, Megan; Baruah, Dhiraj; Aquino, Gilberto; Kabakus, Ismail; Hoelzer, Philipp; Sahbaee, Pooyan; Schoepf, U. Joseph; Burt, Jeremy R.

doi:10.1016/j.heliyon.2022.e08962

Cited by 7 publications

(7 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Principal among these factors was financial constraints such as the cost of a CT scan and distance as major barriers to BC patients receiving CT scans. [26][27][28] However, in the current study, one CT scan per participant was required, any direct costs related to CT scan acquisition were sponsored to remove financial barriers.…”

Section: Discussionmentioning

confidence: 99%

“…However, Kocher et al however reported an association between hypertension and hyperlipidemia and the likelihood of lung metastasis in BC patients using artificial intelligence as a prognostic tool for precision medicine. 26 Different radiological features have been documented. 23,[32][33][34] In most of our cases, the imaging assessment of lung lesions was reported as nodular, with only four cases presenting as consolidation.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Radiologic patterns of distant organ metastasis in advanced breast cancer patients: Prospective review of computed tomography images

Jimah,

Amoako,

Ofori

et al. 2024

Cancer Reports

View full text Add to dashboard Cite

BackgroundBreast cancer (BC) metastases to the abdomen and pelvis affect the liver, mesentery, retroperitoneum, peritoneum, bladder, kidney, ovary, and uterus. The study documented the radiological pattern and features of the chest, bone, abdominal and pelvic (AP) metastases among advanced BC patients.AimThe aim is to document the radiological pattern and features of breast cancer metastasis in the chest, abdomen, pelvis and bones.Materials and ResultsChest, abdominal, and pelvic computed tomography scan images of 36 patients with advanced BC were collated from Cape Coast Teaching Hospital and RAAJ Diagnostics. The images were prospectively assessed for metastasis to the organs of the chest, AP soft tissues, and bones. Radiologic features of metastasis of the lungs, liver, lymph nodes (LNs), and bones were documented. Patients' demographics, clinical data, and histopathology reports were also collected. The data were captured using UVOSYO and exported to Microsoft Excel templates. The data obtained were descriptively analyzed. Only 2.8% of BCs exhibited metaplastic BC, whereas 97.2% had invasive ductal BC. Triple‐negative cases were 55.6%. Of 36 patients, 31 (86.1%), 21 (58.3%), and 14(38.8%) were diagnosed of chest, AP, and bone tissues metastasis, respectively. LN involvement was reported in 26 (72.2%) patients. Majority, 21 (58.3%) were diagnosed of multiple sites metastasis with 15 (41.7%) showing single site. Lungs (77.4%, 24/31) and liver (47.6%, 10/21) were the most affected distant organs. Most bone metastases were lytic lesions (92.9%, 13/14) with the vertebrae (85.7%, 12/14) been the most affected.ConclusionAccording to the study, advanced BC patients have a higher‐than‐average radiologic incidence of lung, liver, bone, and LN metastases.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Radiologic patterns of distant organ metastasis in advanced breast cancer patients: Prospective review of computed tomography images

Jimah,

Amoako,

Ofori

et al. 2024

Cancer Reports

View full text Add to dashboard Cite

show abstract

“…MBIR enables ultra-low-dose diagnostic computed tomography (ULD-CT) of the chest scans with an effective beam dose of about 0.3–0.4 mSv, which approaches the dose of CXR (0.1 mSv). Current advances in artificial intelligence will probably yield ULD-CTs with even further dose reductions 14 and either augment or automate the detection and interpretation of small pulmonary metastases 15 , 16 . In comparison, conventional diagnostic pulmonary CT scan causes an effective beam dose of about 3 mSv 17 .…”

Section: Introductionmentioning

confidence: 99%

Ultra-low-dose computed tomography and chest X-ray in follow-up of high-grade soft tissue sarcoma—a prospective comparative study

Salminen,

Jäämaa,

Nevala

et al. 2024

Sci Rep

View full text Add to dashboard Cite

Ultra-low-dose computed tomography (ULD-CT) may combine the high sensitivity of conventional computed tomography (CT) in detecting sarcoma pulmonary metastasis, with a radiation dose in the same magnitude as chest X-ray (CXR). Fifty patients with non-metastatic high-grade soft tissue sarcoma treated with curative intention were recruited. Their follow-up involved both CXR and ULD-CT to evaluate their different sensitivity. Suspected findings were confirmed by conventional CT if necessary. Patients with isolated pulmonary metastases were treated with surgery or stereotactic body radiation therapy (SBRT) with curative intent if possible. The median effective dose from a single ULD-CT study was 0.27 mSv (range 0.12 to 0.89 mSv). Nine patients were diagnosed with asymptomatic lung metastases during the follow-up. Only three of them were visible in CXR and all nine in ULD-CT. CXR had therefore only a 33% sensitivity compared to ULD-CT. Four patients were operated, and one had SBRT to all pulmonary lesions. Eight of them, however, died of the disease. Two patients developed symptomatic metastatic recurrence involving extrapulmonary sites+/−the lungs between two imaging rounds. ULD-CT has higher sensitivity for the detection of sarcoma pulmonary metastasis than CXR, with a radiation dose considerably lower than conventional CT.Clinical trial registration: NCT05813808. 04-14-2023.

show abstract

“…From 2009 to 2015, evidence accumulated that, if tumors in the breast can be found and treated in the initial stage I, the five-year survival rate can be as high as 98%, but when the disease is detected in a late stage, the five-year survival rate is only 27% [ 1 ], therefore detection and treatment of breast cancer are very important to increase the survival rate. Most of the studies used mammography for breast screening, which did not provide anatomical features, has low sensitivity, and poor positive predictive value [ 4 , 5 , 6 , 7 , 8 , 9 , 10 ]. A good alternative approach, computed tomography (CT), for breast cancer detection, has seen a rapid rise.…”

Section: Introductionmentioning

confidence: 99%

“…It has potential for breast cancer detection using deep neural networks, which represented better detection results [ 7 ]. It can perform well for the detection of breast cancer patient using artificial intelligence and deep learning [ 8 , 9 , 10 ]. Computer-aided diagnosis (CAD) can play a key role in the early detection of breast cancer and effectively reduce the mortality rate of women with breast cancer [ 11 , 12 ].…”

Section: Introductionmentioning

confidence: 99%

Complete, Fully Automatic Detection and Classification of Benign and Malignant Breast Tumors Based on CT Images Using Artificial Intelligent and Image Processing

Kuo

Chen

Barman

et al. 2023

JCM

View full text Add to dashboard Cite

Breast cancer is the most common type of cancer in women, and early detection is important to significantly reduce its mortality rate. This study introduces a detection and diagnosis system that automatically detects and classifies breast tumors in CT scan images. First, the contours of the chest wall are extracted from computed chest tomography images, and two-dimensional image characteristics and three-dimensional image features, together with the application of active contours without edge and geodesic active contours methods, are used to detect, locate, and circle the tumor. Then, the computer-assisted diagnostic system extracts features, quantifying and classifying benign and malignant breast tumors using a greedy algorithm and a support vector machine. The study used 174 breast tumors for experiment and training and performed cross-validation 10 times (k-fold cross-validation) to evaluate performance of the system. The accuracy, sensitivity, specificity, and positive and negative predictive values of the system were 99.43%, 98.82%, 100%, 100%, and 98.89% respectively. This system supports the rapid extraction and classification of breast tumors as either benign or malignant, helping physicians to improve clinical diagnosis.

show abstract

Tumor burden of lung metastases at initial staging in breast cancer patients detected by artificial intelligence as a prognostic tool for precision medicine

Cited by 7 publications

References 28 publications

Radiologic patterns of distant organ metastasis in advanced breast cancer patients: Prospective review of computed tomography images

Radiologic patterns of distant organ metastasis in advanced breast cancer patients: Prospective review of computed tomography images

Ultra-low-dose computed tomography and chest X-ray in follow-up of high-grade soft tissue sarcoma—a prospective comparative study

Complete, Fully Automatic Detection and Classification of Benign and Malignant Breast Tumors Based on CT Images Using Artificial Intelligent and Image Processing

Contact Info

Product

Resources

About