Cribado de cáncer de pulmón: Supervivencia en un amplio programa de detección precoz en España (I-ELCAP) / Lung Cancer Screening: Survival in an Extensive Early Detection Program in Spain (I-ELCAP)

Introducción y objetivo: El cáncer de pulmón (CP) se diagnostica habitualmente en estadios avanzados con una supervivencia media a cinco años del 12%. Ensayos como el National Lung Screening Trial (NLST) y el NEderlands Leuvens longkanker Screenings ONderzoek (NELSON) demuestran una reducción de la mortalidad que justifican la implantación del cribado en población de riesgo. Nuestro objetivo es presentar los resultados de supervivencia del programa de cribado de CP más amplio de España con tomografía computarizada de baja dosis (TCBD). Métodos: Se analizaron los datos del programa Internacional de Detección Precoz de CP (IELCAP) en Valencia, España. Este programa reclutó fumadores o exfumadores con una edad entre 40- 80 años. Se comparan los resultados con otros programas de similar tamaño. Resultados: Un total de 8.278 participantes fueron reclutados con al menos dos rondas de seguimiento, hasta noviembre de 2020 (62,8% varones), realizando una media de seis rondas de cribado por individuo. Diagnosticamos 239 tumores en 12 años de seguimiento. El adenocarcinoma fue el tumor más frecuente con un 61,3% en estadio I. Las tasas de prevalencia e incidencia fueron de 1,5% y 1,4%, respectivamente, con una tasa de detección anual de 0,17. Las tasas de supervivencia cáncer específica a cinco años fueron del 90 y del 80,1% a 10 años. La adherencia fue de 96,84%. Conclusión: La experiencia del programa más amplio de España demuestra que la supervivencia se mejora cuando se realiza en equipos multidisciplinares con experiencia en CP y es similar a programas similares. (AU)

Introduction: Lung cancer (LC) is usually diagnosed at advanced stages with only a 12% 5-year survival. Trials as NLST and NELSON show a mortality decrease, which justifies implementation of lung cancer screening in risk population. Our objective was to show survival results of the largest LC screening program in Spain with low dosage computed tomography (LDCT). Methods: Clinical records from International Early Lung Cancer Detection Program (IELCAP) at Valencia, Spain were analysed. This program recruited volunteers, ever-smokers aged 40-80 years, since 2008. Results are compared to those from other similar sizeable programs. Results: A total of 8278 participants were screened with at least two-rounds until November 2020. A mean of 6 annual screening rounds were performed. We detected 239 tumours along 12-year follow-up. Adenocarcinoma was the most common histology, being 61.3% at stage I. The lung cancer prevalence and incidence proportion was 1.5% and 1.4%, respectively with an annual detection rate of 0.17. One-year survival and 10-year survival were 90% and 80.1%, respectively. Adherence was 96.84%. Conclusion: Largest lung cancer screening in Spain shows that survival is improved when is performed in multidisciplinary team experienced in management of LC, and is comparable to similar screening programs. (AU)

[Translated article] Lung Cancer Screening: Survival in an Extensive Early Detection Program in Spain (I-ELCAP) / Cribado de cáncer de pulmón: supervivencia en un amplio programa de detección precoz en España (I-ELCAP)

Introduction: Lung cancer (LC) is usually diagnosed at advanced stages with only a 12% 5-year survival. Trials as NLST and NELSON show a mortality decrease, which justifies implementation of lung cancer screening in risk population. Our objective was to show survival results of the largest LC screening program in Spain with low dosage computed tomography (LDCT). Methods: Clinical records from International Early Lung Cancer Detection Program (IELCAP) at Valencia, Spain were analysed. This program recruited volunteers, ever-smokers aged 40-80 years, since 2008. Results are compared to those from other similar sizeable programs. Results: A total of 8278 participants were screened with at least two-rounds until November 2020. A mean of 6 annual screening rounds were performed. We detected 239 tumours along 12-year follow-up. Adenocarcinoma was the most common histology, being 61.3% at stage I. The lung cancer prevalence and incidence proportion was 1.5% and 1.4%, respectively with an annual detection rate of 0.17. One-year survival and 10-year survival were 90% and 80.1%, respectively. Adherence was 96.84%. Conclusion: Largest lung cancer screening in Spain shows that survival is improved when is performed in multidisciplinary team experienced in management of LC, and is comparable to similar screening programs. (AU)

Introducción y objetivo: El cáncer de pulmón (CP) se diagnostica habitualmente en estadios avanzados con una supervivencia media a cinco años del 12%. Ensayos como el National Lung Screening Trial (NLST) y el NEderlands Leuvens longkanker Screenings ONderzoek (NELSON) demuestran una reducción de la mortalidad que justifican la implantación del cribado en población de riesgo. Nuestro objetivo es presentar los resultados de supervivencia del programa de cribado de CP más amplio de España con tomografía computarizada de baja dosis (TCBD). Métodos: Se analizaron los datos del programa Internacional de Detección Precoz de CP (IELCAP) en Valencia, España. Este programa reclutó fumadores o exfumadores con una edad entre 40- 80 años. Se comparan los resultados con otros programas de similar tamaño. Resultados: Un total de 8.278 participantes fueron reclutados con al menos dos rondas de seguimiento, hasta noviembre de 2020 (62,8% varones), realizando una media de seis rondas de cribado por individuo. Diagnosticamos 239 tumores en 12 años de seguimiento. El adenocarcinoma fue el tumor más frecuente con un 61,3% en estadio I. Las tasas de prevalencia e incidencia fueron de 1,5% y 1,4%, respectivamente, con una tasa de detección anual de 0,17. Las tasas de supervivencia cáncer específica a cinco años fueron del 90 y del 80,1% a 10 años. La adherencia fue de 96,84%. Conclusión: La experiencia del programa más amplio de España demuestra que la supervivencia se mejora cuando se realiza en equipos multidisciplinares con experiencia en CP y es similar a programas similares. (AU)

Lung Cancer Screening: Survival in an Extensive Early Detection Program in Spain (I-ELCAP). / Cribado de cáncer de pulmón: Supervivencia en un amplio programa de detección precoz en España (I-ELCAP).

INTRODUCTION: Lung cancer (LC) is usually diagnosed at advanced stages with only a 12% 5-year survival. Trials as NLST and NELSON show a mortality decrease, which justifies implementation of lung cancer screening in risk population. Our objective was to show survival results of the largest LC screening program in Spain with low dosage computed tomography (LDCT). METHODS: Clinical records from International Early Lung Cancer Detection Program (IELCAP) at Valencia, Spain were analysed. This program recruited volunteers, ever-smokers aged 40-80 years, since 2008. Results are compared to those from other similar sizeable programs. RESULTS: A total of 8278 participants were screened with at least two-rounds until November 2020. A mean of 6 annual screening rounds were performed. We detected 239 tumours along 12-year follow-up. Adenocarcinoma was the most common histology, being 61.3% at stage I. The lung cancer prevalence and incidence proportion was 1.5% and 1.4%, respectively with an annual detection rate of 0.17. One-year survival and 10-year survival were 90% and 80.1%, respectively. Adherence was 96.84%. CONCLUSION: Largest lung cancer screening in Spain shows that survival is improved when is performed in multidisciplinary team experienced in management of LC, and is comparable to similar screening programs.

Deep learning for fully automatic detection, segmentation, and Gleason grade estimation of prostate cancer in multiparametric magnetic resonance images.

Although the emergence of multi-parametric magnetic resonance imaging (mpMRI) has had a profound impact on the diagnosis of prostate cancers (PCa), analyzing these images remains still complex even for experts. This paper proposes a fully automatic system based on Deep Learning that performs localization, segmentation and Gleason grade group (GGG) estimation of PCa lesions from prostate mpMRIs. It uses 490 mpMRIs for training/validation and 75 for testing from two different datasets: ProstateX and Valencian Oncology Institute Foundation. In the test set, it achieves an excellent lesion-level AUC/sensitivity/specificity for the GGG[Formula: see text]2 significance criterion of 0.96/1.00/0.79 for the ProstateX dataset, and 0.95/1.00/0.80 for the IVO dataset. At a patient level, the results are 0.87/1.00/0.375 in ProstateX, and 0.91/1.00/0.762 in IVO. Furthermore, on the online ProstateX grand challenge, the model obtained an AUC of 0.85 (0.87 when trained only on the ProstateX data, tying up with the original winner of the challenge). For expert comparison, IVO radiologist's PI-RADS 4 sensitivity/specificity were 0.88/0.56 at a lesion level, and 0.85/0.58 at a patient level. The full code for the ProstateX-trained model is openly available at https://github.com/OscarPellicer/prostate_lesion_detection . We hope that this will represent a landmark for future research to use, compare and improve upon.

Diagnóstico precoz del cáncer de pulmón: utilidad de la tomografía computarizada de baja dosis de radiación / Lung Cancer Screening: Use of Low-Dose Computed Tomography

Introducción: El pronóstico del cáncer de pulmón (CP) está relacionado directamente con el estadio de la enfermedad al diagnóstico. Material y métodos: Realizamos TC de baja dosis (TCBD) a personas asintomáticas ≥ 50 años, fumadores o exfumadores de ≥ 10 paquetes-año, sin antecedentes oncológicos. Seguimos un algoritmo de evaluación según el tamaño y la morfología de los nódulos. En los CP diagnosticados se estableció el tratamiento adecuado y el seguimiento fue de 5 años. Resultados: Estudiamos 4.951 personas (65,4% varones) con una media de edad de 56,89 ± 5,26 años; 550 presentaron nódulos. De 3.891 nódulos detectados, 692 (19,57%) fueron considerados positivos, hallando 38 tumores (36 CP). En el estudio anual, 224 sujetos mostraban algún nódulo, siendo 288 (7,91%) positivos (13 CP). En el 80% el control se realizó con TCBD y se indicó biopsia en el 5,8% (basal) y 7,6% (anual) de los nódulos positivos. La prevalencia fue del 0,89 y la incidencia del 0,1%. La sensibilidad, la especificidad, el VPP y el VPN en el estudio basal fueron del 92,31, del 89,54, del 6,55 y del 99,93%, respectivamente, y en el anual, del 76,92, del 95,7, del 4,52 y del 99,94%, respectivamente. Se detectaron 52 tumores (49 CP), 25 (52,08%) en estadio I. La supervivencia global de los CP fue del 58,5% a los 5 años, y la supervivencia cáncer específica, del 67,1% (75,8% en los pacientes quirúrgicos). Conclusiones: La TCBD integrada en un programa elaborado de detección y evaluación de nódulos es una herramienta útil para diagnosticar CP en estadio precoz

Introduction: The prognosis of lung cancer (LC) correlates directly with the stage of the disease at the time of diagnosis. Material and methods: We performed low-dose CT (LDCT) in asymptomatic individuals ≥ 50 years old, smokers or former smokers of ≥ 10 pack-years, with no history of cancer. We followed an evaluation algorithm, according to the size and morphology of the nodules. The appropriate treatment for the LC diagnosis was given and patients were followed up for 5 years. Results: We studied 4,951 individuals (65.4% males) with an average age of 56.89 ± 5.26 years; 550 presented nodules. Of the 3,891 nodules detected, 692 (19.57%) were considered positive, and 38 tumors (36 LC) were identified. In the annual follow-up, nodules were found in 224 subjects, 288 (7.91%) of which were positive (13 LC). In 80%, the study was performed with LDCT, and biopsy was indicated in 5.8% (baseline) and in 7.6% (annual) of the positive nodules. Prevalence was 0.89 and incidence was 0.1%. The sensitivity, specificity, PPV and NPV in the baseline study were 92.31, 89.54, 6.55 and 99.93%, respectively, and in the annual study, they were 76.92, 95.7, 4.52 and 99.94%, respectively. A total of 52 tumors were detected (49 LC), 25 (52.08%) in stage I. The 5-year overall survival rate for LC was 58.5% and cancer-specific survival was 67.1% (75.8% in surgical patients). Conclusion: LDCT integrated into an elaborate nodule detection and evaluation program is a useful tool for diagnosing early-stage LC

Lung Cancer Screening: Use of Low-Dose Computed Tomography. / Diagnóstico precoz del cáncer de pulmón: utilidad de la tomografía computarizada de baja dosis de radiación.

INTRODUCTION: The prognosis of lung cancer (LC) correlates directly with the stage of the disease at the time of diagnosis. MATERIAL AND METHODS: We performed low-dose CT (LDCT) in asymptomatic individuals ≥50years old, smokers or former smokers of ≥10 pack-years, with no history of cancer. We followed an evaluation algorithm, according to the size and morphology of the nodules. The appropriate treatment for the LC diagnosis was given and patients were followed up for 5years. RESULTS: We studied 4,951 individuals (65.4% males) with an average age of 56.89±5.26years; 550 presented nodules. Of the 3,891 nodules detected, 692 (19.57%) were considered positive, and 38 tumors (36LC) were identified. In the annual follow-up, nodules were found in 224 subjects, 288 (7.91%) of which were positive (13LC). In 80%, the study was performed with LDCT, and biopsy was indicated in 5.8% (baseline) and in 7.6% (annual) of the positive nodules. Prevalence was 0.89 and incidence was 0.1%. The sensitivity, specificity, PPV and NPV in the baseline study were 92.31, 89.54, 6.55 and 99.93%, respectively, and in the annual study, they were 76.92, 95.7, 4.52 and 99.94%, respectively. A total of 52 tumors were detected (49LC), 25 (52.08%) in stageI. The 5-year overall survival rate for LC was 58.5% and cancer-specific survival was 67.1% (75.8% in surgical patients). CONCLUSION: LDCT integrated into an elaborate nodule detection and evaluation program is a useful tool for diagnosing early-stage LC.