Accurate Evaluation of Feature Contributions for Sentinel Lymph Node Status Classification in Breast Cancer
The current guidelines recommend the sentinel lymph node biopsy to evaluate the lymph node involvement for breast cancer patients with clinically negative lymph nodes on clinical or radiological examination. Machine learning (ML) models have significantly improved the prediction of lymph nodes statu...
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-07-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/14/7227 |
| _version_ | 1797407587602268160 |
|---|---|
| author | Angela Lombardi Nicola Amoroso Loredana Bellantuono Samantha Bove Maria Colomba Comes Annarita Fanizzi Daniele La Forgia Vito Lorusso Alfonso Monaco Sabina Tangaro Francesco Alfredo Zito Roberto Bellotti Raffaella Massafra |
| author_facet | Angela Lombardi Nicola Amoroso Loredana Bellantuono Samantha Bove Maria Colomba Comes Annarita Fanizzi Daniele La Forgia Vito Lorusso Alfonso Monaco Sabina Tangaro Francesco Alfredo Zito Roberto Bellotti Raffaella Massafra |
| author_sort | Angela Lombardi |
| collection | DOAJ |
| description | The current guidelines recommend the sentinel lymph node biopsy to evaluate the lymph node involvement for breast cancer patients with clinically negative lymph nodes on clinical or radiological examination. Machine learning (ML) models have significantly improved the prediction of lymph nodes status based on clinical features, thus avoiding expensive, time-consuming and invasive procedures. However, the classification of sentinel lymph node status represents a typical example of an unbalanced classification problem. In this work, we developed a ML framework to explore the effects of unbalanced populations on the performance and stability of feature ranking for sentinel lymph node status classification in breast cancer. Our results indicate state-of-the-art AUC (Area under the Receiver Operating Characteristic curve) values on a hold-out set (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>67</mn><mo>%</mo></mrow></semantics></math></inline-formula>) while providing particularly stable features related to tumor size, histological subtype and estrogen receptor expression, which should therefore be considered as potential biomarkers. |
| first_indexed | 2024-03-09T03:43:42Z |
| format | Article |
| id | doaj.art-aaf36b281ca24345804fe579e8cb3e10 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T03:43:42Z |
| publishDate | 2022-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-aaf36b281ca24345804fe579e8cb3e102023-12-03T14:37:13ZengMDPI AGApplied Sciences2076-34172022-07-011214722710.3390/app12147227Accurate Evaluation of Feature Contributions for Sentinel Lymph Node Status Classification in Breast CancerAngela Lombardi0Nicola Amoroso1Loredana Bellantuono2Samantha Bove3Maria Colomba Comes4Annarita Fanizzi5Daniele La Forgia6Vito Lorusso7Alfonso Monaco8Sabina Tangaro9Francesco Alfredo Zito10Roberto Bellotti11Raffaella Massafra12Dipartimento Interateneo di Fisica, Università degli Studi di Bari, Via E. Orabona 4, 70125 Bari, ItalyIstituto Nazionale di Fisica Nucleare, Sezione di Bari, Via E. Orabona 4, 70125 Bari, ItalyIstituto Nazionale di Fisica Nucleare, Sezione di Bari, Via E. Orabona 4, 70125 Bari, ItalyI.R.C.C.S. Istituto Tumori “Giovanni Paolo II”, Viale Orazio Flacco 65, 70124 Bari, ItalyI.R.C.C.S. Istituto Tumori “Giovanni Paolo II”, Viale Orazio Flacco 65, 70124 Bari, ItalyI.R.C.C.S. Istituto Tumori “Giovanni Paolo II”, Viale Orazio Flacco 65, 70124 Bari, ItalyI.R.C.C.S. Istituto Tumori “Giovanni Paolo II”, Viale Orazio Flacco 65, 70124 Bari, ItalyI.R.C.C.S. Istituto Tumori “Giovanni Paolo II”, Viale Orazio Flacco 65, 70124 Bari, ItalyDipartimento Interateneo di Fisica, Università degli Studi di Bari, Via E. Orabona 4, 70125 Bari, ItalyIstituto Nazionale di Fisica Nucleare, Sezione di Bari, Via E. Orabona 4, 70125 Bari, ItalyI.R.C.C.S. Istituto Tumori “Giovanni Paolo II”, Viale Orazio Flacco 65, 70124 Bari, ItalyDipartimento Interateneo di Fisica, Università degli Studi di Bari, Via E. Orabona 4, 70125 Bari, ItalyI.R.C.C.S. Istituto Tumori “Giovanni Paolo II”, Viale Orazio Flacco 65, 70124 Bari, ItalyThe current guidelines recommend the sentinel lymph node biopsy to evaluate the lymph node involvement for breast cancer patients with clinically negative lymph nodes on clinical or radiological examination. Machine learning (ML) models have significantly improved the prediction of lymph nodes status based on clinical features, thus avoiding expensive, time-consuming and invasive procedures. However, the classification of sentinel lymph node status represents a typical example of an unbalanced classification problem. In this work, we developed a ML framework to explore the effects of unbalanced populations on the performance and stability of feature ranking for sentinel lymph node status classification in breast cancer. Our results indicate state-of-the-art AUC (Area under the Receiver Operating Characteristic curve) values on a hold-out set (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>67</mn><mo>%</mo></mrow></semantics></math></inline-formula>) while providing particularly stable features related to tumor size, histological subtype and estrogen receptor expression, which should therefore be considered as potential biomarkers.https://www.mdpi.com/2076-3417/12/14/7227sentinel lymph nodeimbalanced datasetdata augmentationbreast cancermachine learninginterpretability |
| spellingShingle | Angela Lombardi Nicola Amoroso Loredana Bellantuono Samantha Bove Maria Colomba Comes Annarita Fanizzi Daniele La Forgia Vito Lorusso Alfonso Monaco Sabina Tangaro Francesco Alfredo Zito Roberto Bellotti Raffaella Massafra Accurate Evaluation of Feature Contributions for Sentinel Lymph Node Status Classification in Breast Cancer Applied Sciences sentinel lymph node imbalanced dataset data augmentation breast cancer machine learning interpretability |
| title | Accurate Evaluation of Feature Contributions for Sentinel Lymph Node Status Classification in Breast Cancer |
| title_full | Accurate Evaluation of Feature Contributions for Sentinel Lymph Node Status Classification in Breast Cancer |
| title_fullStr | Accurate Evaluation of Feature Contributions for Sentinel Lymph Node Status Classification in Breast Cancer |
| title_full_unstemmed | Accurate Evaluation of Feature Contributions for Sentinel Lymph Node Status Classification in Breast Cancer |
| title_short | Accurate Evaluation of Feature Contributions for Sentinel Lymph Node Status Classification in Breast Cancer |
| title_sort | accurate evaluation of feature contributions for sentinel lymph node status classification in breast cancer |
| topic | sentinel lymph node imbalanced dataset data augmentation breast cancer machine learning interpretability |
| url | https://www.mdpi.com/2076-3417/12/14/7227 |
| work_keys_str_mv | AT angelalombardi accurateevaluationoffeaturecontributionsforsentinellymphnodestatusclassificationinbreastcancer AT nicolaamoroso accurateevaluationoffeaturecontributionsforsentinellymphnodestatusclassificationinbreastcancer AT loredanabellantuono accurateevaluationoffeaturecontributionsforsentinellymphnodestatusclassificationinbreastcancer AT samanthabove accurateevaluationoffeaturecontributionsforsentinellymphnodestatusclassificationinbreastcancer AT mariacolombacomes accurateevaluationoffeaturecontributionsforsentinellymphnodestatusclassificationinbreastcancer AT annaritafanizzi accurateevaluationoffeaturecontributionsforsentinellymphnodestatusclassificationinbreastcancer AT danielelaforgia accurateevaluationoffeaturecontributionsforsentinellymphnodestatusclassificationinbreastcancer AT vitolorusso accurateevaluationoffeaturecontributionsforsentinellymphnodestatusclassificationinbreastcancer AT alfonsomonaco accurateevaluationoffeaturecontributionsforsentinellymphnodestatusclassificationinbreastcancer AT sabinatangaro accurateevaluationoffeaturecontributionsforsentinellymphnodestatusclassificationinbreastcancer AT francescoalfredozito accurateevaluationoffeaturecontributionsforsentinellymphnodestatusclassificationinbreastcancer AT robertobellotti accurateevaluationoffeaturecontributionsforsentinellymphnodestatusclassificationinbreastcancer AT raffaellamassafra accurateevaluationoffeaturecontributionsforsentinellymphnodestatusclassificationinbreastcancer |