Discriminating healthy from tumor tissue in breast lumpectomy specimens using deep learning-based hyperspectral imaging

Jong, Lynn-Jade; Kruif, Naomi de; Geldof, Freija; Veluponnar, Dinusha; Sanders, Joyce; Peeters-Baas, Marie-Jeanne Vrancken; Duijnhoven, Frederieke van; Sterenborg, Henricus J. C. M.; Dashtbozorg, Behdad; Ruers, Theo J.M.

doi:10.1364/boe.455208

Cited by 12 publications

(16 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hyperspectral imaging (HSI) is a technique that has shown promising results for the discrimination between tumor and healthy tissue in the breast [9][10][11][12][13][14], as well as in the colon [15,16], ovary [17], thyroid [18,19], and skin [20,21]. Hyperspectral imaging is a diagnostic technique in which digital imaging is combined with spectroscopy.…”

Section: Introductionmentioning

confidence: 99%

“…Hyperspectral imaging has been shown to be able to differentiate healthy from malignant tissue in gross-sectioned breast tissue slices using supervised classification methods [9][10][11]. In a study by Kho et al, promising results were achieved with a sensitivity and specificity of, respectively, 98% and 99% for discriminating tumor tissue from healthy tissue in breast tissue slices [10].…”

Section: Introductionmentioning

confidence: 99%

“…Even so, a tissue classification algorithm developed on tissue slices cannot be directly used for intact resection specimens. Previous studies demonstrated differences between slices and specimens in terms of tissue thickness, freshness, surface structure, blood saturation, and cauterization, which in turn can influence the measured spectra within the hyperspectral images [11,22]. Therefore, we recently took the next step towards clinical translation by developing an algorithm specifically for breast cancer resection specimens [11].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Tissue Classification of Breast Cancer by Hyperspectral Unmixing

Jong

Post

Veluponnar

et al. 2023

Cancers

Self Cite

View full text Add to dashboard Cite

(1) Background: Assessing the resection margins during breast-conserving surgery is an important clinical need to minimize the risk of recurrent breast cancer. However, currently there is no technique that can provide real-time feedback to aid surgeons in the margin assessment. Hyperspectral imaging has the potential to overcome this problem. To classify resection margins with this technique, a tissue discrimination model should be developed, which requires a dataset with accurate ground-truth labels. However, establishing such a dataset for resection specimens is difficult. (2) Methods: In this study, we therefore propose a novel approach based on hyperspectral unmixing to determine which pixels within hyperspectral images should be assigned to the ground-truth labels from histopathology. Subsequently, we use this hyperspectral-unmixing-based approach to develop a tissue discrimination model on the presence of tumor tissue within the resection margins of ex vivo breast lumpectomy specimens. (3) Results: In total, 372 measured locations were included on the lumpectomy resection surface of 189 patients. We achieved a sensitivity of 0.94, specificity of 0.85, accuracy of 0.87, Matthew’s correlation coefficient of 0.71, and area under the curve of 0.92. (4) Conclusion: Using this hyperspectral-unmixing-based approach, we demonstrated that the measured locations with hyperspectral imaging on the resection surface of lumpectomy specimens could be classified with excellent performance.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Tissue Classification of Breast Cancer by Hyperspectral Unmixing

Jong

Post

Veluponnar

et al. 2023

Cancers

Self Cite

View full text Add to dashboard Cite

show abstract

“…In recent years, this method has gained wide application in the medical field and is of interest to researchers in the field of biophotonics. HSI has been used in both in vivo and in vitro cancer detection, such as brain [23], colorectal [24], breast [25], and cervical cancer detection [26]. HSI is also used in the detection of healed skin tissue burns [27], diabetic foot detection [28], and retinopathy detection [29].…”

Section: Introductionmentioning

confidence: 99%

Discrimination between normal and necrotic small intestinal tissue using hyperspectral imaging and unsupervised classification

Zhang

Huang

Chen

et al. 2023

Journal of Biophotonics

View full text Add to dashboard Cite

Objective and automatic clinical discrimination of normal and necrotic sites of small intestinal tissue remains challenging. In this study, hyperspectral imaging (HSI) and unsupervised classification techniques were used to distinguish normal and necrotic sites of small intestinal tissues. Small intestinal tissue hyperspectral images of eight Japanese large‐eared white rabbits were acquired using a visible near‐infrared hyperspectral camera, and K‐means and density peaks (DP) clustering algorithms were used to differentiate between normal and necrotic tissue. The three cases in this study showed that the average clustering purity of the DP clustering algorithm reached 92.07% when the two band combinations of 500–622 and 700–858 nm were selected. The results of this study suggest that HSI and DP clustering can assist physicians in distinguishing between normal and necrotic sites in the small intestine in vivo.

show abstract

“…In recent years, HSI has been widely used to image human and animal tumors in brain [8,9,[11][12][13][14][15][16][17][18][19][20][21][22], breast [8,9,11,[23][24][25][26][27][28], colon [8,9,11,[29][30][31][32][33], prostate [8,9,11,34,35] and skin [8,9,11,[36][37][38][39][40][41][42]. The main shortcoming of most studies utilizing HSI is that they analyze images of histopathological slides to detect tumor cells ex vivo.…”

Section: Introductionmentioning

confidence: 99%