Non-invasive and real-time proliferative activity estimation based on a quantitative radiomics approach for patients with acromegaly: a multicenter study

BACKGROUND

Proliferative activity prediction is important for determining individual treatment strategies for patients with acromegaly, and tumor proliferative activity is usually measured by the expression of Ki-67.

OBJECTIVE

This study aimed to assess the value of a magnetic resonance imaging (MRI)-based radiomics approach in predicting the Ki-67 index of acromegaly patients.

METHODS

A total of 138 patients with acromegaly were retrospectively reviewed and randomly assigned to primary and validation cohorts. Radiomics features were extracted from MR images, and then the elastic net and recursive feature elimination algorithms were applied to determine critical radiomics features for constructing a radiomics signature. Subsequently, multivariable logistic regression analysis was used to select the most informative clinical features, and a radiomics nomogram incorporating a radiomics signature and selected clinical features was constructed for individual predictions. Twenty-five acromegaly patients were enrolled for multicenter model validation.

RESULTS

Seventeen radiomics features were selected to construct a radiomics signature that achieved an area under the curve (AUC) value of 0.96 and 0.89 in the primary cohort and the validation cohort, respectively. A radiomics nomogram that incorporated the radiomics signature and eight selected clinical features was constructed and showed good discrimination and calibration, with an AUC of 0.94 in the primary cohort and 0.91 in the validation cohort. The radiomics signature in the multicenter validation achieved an accuracy of 88.2%. The analysis of the decision curve showed that the radiomics signature and radiomics nomogram were clinically useful for patients with acromegaly.

CONCLUSIONS

The radiomics signature developed in this study could aid neurosurgeons in predicting the Ki-67 index of patients with acromegaly and could contribute to non-invasive measurement of proliferative activity, affecting individual treatment strategies.

Abstract PD2-13: Benefits to breast screening beyond mortality reduction

Background

The value of population-based mammographic screening has been questioned by those who believe that the reduction in mortality from earlier diagnosis is outweighed by harms including overdiagnosis and overtreatment. Much of these commentaries assume that all Early-Stage Breast Cancer (ESBC) is treated the same way after diagnosis; with extensive therapies including surgery, radiotherapy and chemotherapy being standard.

Intensity of treatment received is rarely mentioned in the debate. We hypothesised that those diagnosed through a screening program (Active Screeners (AS)) would receive less extensive surgical treatment and less intense adjuvant therapies than those not recently screened (NRS). If demonstrated, these differences would form an important component of the debate over the role of mammographic screening.

Methods

Retrospective analysis of a consecutive cohort of female patients aged 50-69 and managed for ESBC (invasive or DCIS) during 2007-2013 within a large metropolitan Breast Service, diagnosed either via a population screening program (AS) or outside of the program (NRS). Data on patient characteristics, symptoms, mode of detection, tumour pathology, surgical intervention and adjuvant treatment recommendations were derived from prospectively collected Multi-Disciplinary Meeting (MDM) records. Patients with metastatic disease or prior treatment for breast cancer were excluded.

Results

791 cases were identified (569 with screen-detected cancer, 53 with interval cancers and 169 cancers diagnosed in women not recently screened). Invasive cancers in the AS group were much smaller than in the NRS group – mean 17mm versus 26mm. The AS group had lower grade invasive cancer – grade 1, 2 and 3 were 27%, 42%, 31% - compared with 10%, 39% and 52% in the NRS group. The AS group were more likely to have ER+ve cancers (88% vs 80%) and less likely to have nodal involvement (26% vs 48%). For invasive breast cancer, the NRS group were more than twice as likely to undergo mastectomy than cancers in the AS group (35% vs 16%). Axillary dissections were more common in the NRS than the AS group (43% vs 19%). Adjuvant chemotherapy was recommended more frequently for the NRS group compared to the AS group (65% vs 37%), as was post mastectomy radiotherapy (58% vs 39%). Endocrine therapy was less often recommended to the NRS group (86% versus 77%).

Conclusion

Women diagnosed with early stage breast cancer who are participating in a population based screening program are less likely to receive mastectomy and/or axillary dissection, less likely to receive adjuvant chemotherapy and less likely to receive post-mastectomy radiotherapy. These differences in treatment intensity should be considered in the debate surrounding mammographic screening.

Citation Format: Elder KJ, Nickson C, Cooke S, Machalek D, Rose A, Mou A, Collins JP, Park A, De Boer R, Phillips C, Pridmore V, Farrugia H, Mann GB. Benefits to breast screening beyond mortality reduction [abstract]. In: Proceedings of the 2017 San Antonio Breast Cancer Symposium; 2017 Dec 5-9; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2018;78(4 Suppl):Abstract nr PD2-13.

Assessment of the Likelihood of Invasive Breast Cancer When Core Needle Biopsy Shows DCIS

Background: Ductal carcinoma in-situ (DCIS) on core needle biopsy (CNB) may be associated with a final diagnosis of invasive cancer (IC). As patients with IC need axillary assessment, those at risk of upstaging may be appropriate for sentinel node biopsy (SNB) at initial surgery, preventing the need for re-operation. We assessed this risk using pre-operative factors to develop a management algorithm.Materials and Methods: All patients whose CNB showed DCIS or DCIS with microinvasion (DCISm) from a single population-based breast screening program in Australia between 1994 and 2006 were studied. Medical records were reviewed for demographic, radiologic, clinical and pathologic data.Results: 11 of 15 DCISm cases (73.3%) and 65 of 375 DCIS cases (17.3%) were upstaged to IC. Microinvasion on CNB overwhelmingly predicted presence of frank invasive cancer. For cases of DCIS, multivariate analysis showed that (1) palpability (p=0.009), (2) large mammographic size ≥20mm (p=0.001) and (3) prolonged screening interval ≥3 years (p=0.008) were associated with upstaging. On univariate analysis, (4) non-calcific mammographic features (mass, architectural distortion or non-specific density) were significantly associated with upstaging (p=0.001). There was a trend towards upstaging in patients with high grade DCIS on CNB (p=0.07). Factors not associated with upstaging were microcalcifications (p=0.12), comedonecrosis (p=0.14), age (p=0.38) and CNB method (p=0.50). The rate of upstaging increases with the number of associated risk factors present in a patient: 8.3% in patients with no risk factors, 21.2% in those with one risk factor, 38.6% in those with two risk factors, and 52.9% in those with three risk factors. 13 patients (3.3%) had lymph node metastases.Conclusions: The risk of upstaging can be estimated using pre-operative features in patients with DCIS on CNB. We propose a management algorithm that includes SNB for DCIS patients: with microinvasion on core biopsy, with two or more predictive factors, and those with planned total mastectomy.

Citation Information: Cancer Res 2009;69(24 Suppl):Abstract nr 3111.