Detection of acini in histopathology slides: towards automated prediction of breast cancer risk

Wetstein, Suzanne C.; Onken, Allison; Baker, Gabrielle M.; Pyle, Michael E.; Pluim, Josien P. W.; Tamimi, Rulla M.; Heng, Yujing J.; Veta, Mitko

doi:10.1117/12.2511408

Cited by 4 publications

(14 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There was slightly more agreement in the evaluation of Russo et al [2] predominant lobule type compared to Baer et al…”

Section: Qualitative Measures: Intra-and Inter-observer Agreementmentioning

confidence: 67%

“…All quantitative measures were significantly different between pre-and post-menopausal women, except number of TDLUs per tissue area 13 evaluated by the automated method (p=0.06). Likewise, qualitative measures (consensus vote by observers and automated method) were significantly different between pre-and postmenopausal women, except lobular classification according to Baer et al [2] assessed by the automated method (p=0.07). No participant was classified as predominantly type 3 according to Russo et al [2].…”

Section: Tdlu Involution With Age and Menopausal Statusmentioning

confidence: 82%

“…This method can determine the three standardized quantitative measures by Figueroa et al (i.e., TDLUs/mm 2 , median TDLU span (µm), and median acini/TDLU [4, 10, 13, 14]) as well as two additional quantitative measures: number of acini per tissue area (acini/mm 2 ) and median TDLU area (mm 2 ). Our method can also perform TDLU involution assessment using qualitative categories as described by Russo et al [2] (i.e., predominant lobule type 1, 2 or 3) and Baer et al…”

Section: Developing the Automated Methods For Tdlu Involution Measuresmentioning

confidence: 99%

“…Acini with elongated shape or no lumen were excluded. Three observers performed qualitative assessments using predominant lobule type by Russo et al [2] and categories by Baer et al [9]. For intra-observer evaluation, 10 out of 40 WSIs were randomly chosen for re-assessment.…”

Section: Validating the Automated Measures Of Tdlu Involutionmentioning

confidence: 99%

“…Most benign breast lesions and breast cancers arise in the terminal duct lobular units (TDLUs) [1], the milk-producing structures of the breast. Russo et al [2] historically classified TDLUs into four lobule types: type 1 (least developed; <12 acini/lobule), type 2 (evolves from type 1;…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Deep learning assessment of breast terminal duct lobular unit involution: Towards automated prediction of breast cancer risk

et al. 2020

Self Cite

View full text Add to dashboard Cite

Terminal ductal lobular unit (TDLU) involution is the regression of milk-producing structures in the breast. Women with less TDLU involution are more likely to develop breast cancer. A major bottleneck in studying TDLU involution in large cohort studies is the need for laborintensive manual assessment of TDLUs. We developed a computational pathology solution to automatically capture TDLU involution measures.Whole slide images (WSIs) of benign breast biopsies were obtained from the Nurses' Health Study (NHS). A first set of 92 WSIs was annotated for TDLUs, acini and adipose tissue to train deep convolutional neural network (CNN) models for detection of acini, and segmentation of TDLUs and adipose tissue. These networks were integrated into a single computational method to capture TDLU involution measures including number of TDLUs per tissue area (mm 2 ), median TDLU span (µm) and median number of acini per TDLU. We validated our method on 40 additional WSIs by comparing with manually acquired measures.Our CNN models detected acini with an F1 score of 0.73±0.09, and segmented TDLUs and adipose tissue with Dice scores of 0.86±0.11 and 0.86±0.04, respectively. The inter-observer ICC scores for manual assessments on 40 WSIs of number of TDLUs per tissue area, median TDLU span, and median acini count per TDLU were 0.71, 95% CI [0.51, 0.83], 0.81, 95% CI [0.67, 0.90], and 0.73, 95% CI [0.54, 0.85], respectively. Intra-observer reliability was evaluated on 10/40 WSIs with ICC scores of >0.8. Inter-observer ICC scores between automated results and the mean of the two observers were: 0.80, 95% CI [0.63, 0.90] for number of TDLUs per tissue area, 0.57, 95% CI [0.19, 0.77] for median TDLU span, and 0.80, 95% CI [0.62, 0.89] for median acini count per TDLU. TDLU involution measures evaluated by manual and automated assessment were inversely associated with age and menopausal status.We have developed a computational pathology method to measure TDLU involution. This technology eliminates the labor-intensiveness and subjectivity of manual TDLU assessment, and can be applied to future breast cancer risk studies. Wetstein et al. 3

show abstract

“…There was slightly more agreement in the evaluation of Russo et al [2] predominant lobule type compared to Baer et al…”

Section: Qualitative Measures: Intra-and Inter-observer Agreementmentioning

confidence: 67%

Section: Tdlu Involution With Age and Menopausal Statusmentioning

confidence: 82%

Section: Developing the Automated Methods For Tdlu Involution Measuresmentioning

confidence: 99%

Section: Validating the Automated Measures Of Tdlu Involutionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Deep learning assessment of breast terminal duct lobular unit involution: Towards automated prediction of breast cancer risk

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

Deep Learning Image Analysis of Benign Breast Disease to Identify Subsequent Risk of Breast Cancer

Vellal

Sirinukunwattan

Kensler

et al. 2021

JNCI Cancer Spectrum

Self Cite

View full text Add to dashboard Cite

Background New biomarkers of risk may improve breast cancer (BC) risk prediction. We developed a computational pathology method to segment benign breast disease (BBD) whole slide images into epithelium, fibrous stroma, and fat. We applied our method to the BBD BC nested case-control study within the Nurses’ Health Studies to assess whether computer-derived tissue composition or a morphometric signature was associated with subsequent risk of BC. Methods Tissue segmentation and nuclei detection deep-learning networks were established and applied to 3795 whole slide images from 293 cases who developed BC and 1132 controls who did not. Percentages of each tissue region were calculated, and 615 morphometric features were extracted. Elastic net regression was used to create a BC morphometric signature. Associations between BC risk factors and age-adjusted tissue composition among controls were assessed using analysis of covariance. Unconditional logistic regression, adjusting for the matching factors, BBD histological subtypes, parity, menopausal status, and body mass index evaluated the relationship between tissue composition and BC risk. All statistical tests were 2-sided. Results Among controls, direction of associations between BBD subtypes, parity, and number of births with breast composition varied by tissue region; select regions were associated with childhood body size, body mass index, age of menarche, and menopausal status (all P < .05). A higher proportion of epithelial tissue was associated with increased BC risk (odds ratio = 1.39, 95% confidence interval = 0.91 to 2.14, for highest vs lowest quartiles, Ptrend = .047). No morphometric signature was associated with BC. Conclusions The amount of epithelial tissue may be incorporated into risk assessment models to improve BC risk prediction.

show abstract

Deep Learning Image Analysis of Benign Breast Disease to Identify Subsequent Risk of Breast Cancer

Vellal

Sirinukunwattana

Kensler

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Background New biomarkers of risk may improve breast cancer risk prediction. We developed a computational pathology method to segment benign breast disease (BBD) whole slide images (WSIs) into epithelium, fibrous stroma, and fat. We applied our method to the BBD breast cancer nested case-control study within the Nurses' Health Studies to assess whether computer-derived tissue composition or a morphometric signature was associated with subsequent risk of breast cancer. Methods Tissue segmentation and nuclei detection deep-learning networks were established and applied to 3795 WSIs from 293 cases who developed breast cancer and 1132 controls who did not. Percentages of each tissue region were calculated and 615 morphometric features were extracted. Elastic net regression was used to create a breast cancer morphometric signature. Associations between breast cancer risk factors and age-adjusted tissue composition among controls were assessed using analysis of covariance. Unconditional logistic regression, adjusting for the matching factors, BBD histological subtypes, parity, menopausal status, and BMI evaluated the relationship between tissue composition and breast cancer risk. Results Among controls, BBD subtypes, parity, and number of births were differentially associated with all three tissue regions (p<0.05); select regions were associated with childhood body size, BMI, age of menarche, and menopausal status (p<0.05). Higher proportion of epithelial tissue was associated with increased breast cancer risk (OR=1.39, 95% CI 0.91-2.14 comparing highest and lowest quartiles; p-trend<0.05). No morphometric signature was associated with breast cancer. Conclusion The amount of epithelial tissue may be incorporated into risk assessment models to improve breast cancer risk prediction.

show abstract

Detection of acini in histopathology slides: towards automated prediction of breast cancer risk

Cited by 4 publications

References 3 publications

Deep learning assessment of breast terminal duct lobular unit involution: Towards automated prediction of breast cancer risk

Deep learning assessment of breast terminal duct lobular unit involution: Towards automated prediction of breast cancer risk

Deep Learning Image Analysis of Benign Breast Disease to Identify Subsequent Risk of Breast Cancer

Deep Learning Image Analysis of Benign Breast Disease to Identify Subsequent Risk of Breast Cancer

Contact Info

Product

Resources

About